arXiv subjects

Raju Gottumukkala

Publications and source records attributed to Raju Gottumukkala.

14 recordsLinked to original sources

arXiv2026

Towards an Adaptive Social Game-Playing Robot: An Offline Reinforcement Learning-Based Framework

HRI research increasingly demands robots that go beyond task execution to respond meaningfully to user emotions. This is especially needed when supporting students with learning difficulties in game-based learning scenarios. Here, the objective of these robots is to train users with game-playing skills, and this requires robots to get input about users' interests and engagement. In this paper, we present a system for an adaptive social game-playing robot. However, creating such an agent through online RL requires extensive real-world training data and potentially be uncomfortable for users. To address this, we investigate offline RL as a safe and efficient alternative. We introduce a system architecture that integrates multimodal emotion recognition and adaptive robotic responses. We also evaluate the performance of various offline RL algorithms using a dataset collected from a real-world human-robot game-playing scenario. Our results indicate that BCQ and DDQN offer the greatest robustness to hyperparameter variations, whereas CQL is the most effective at mitigating overestimation bias. Through this research, we aim to inform the selection and design of reliable offline RL policies for real-world social robotics. Ultimately, this work provides a foundational step toward creating socially intelligent agents that can learn complex and emotion-adaptive behaviors entirely from offline datasets, ensuring both human comfort and practical scalability.

cs.RO↗

arXiv2025

Physics-Guided Fusion for Robust 3D Tracking of Fast Moving Small Objects

While computer vision has advanced considerably for general object detection and tracking, the specific problem of fast-moving tiny objects remains underexplored. This paper addresses the significant challenge of detecting and tracking rapidly moving small objects using an RGB-D camera. Our novel system combines deep learning-based detection with physics-based tracking to overcome the limitations of existing approaches. Our contributions include: (1) a comprehensive system design for object detection and tracking of fast-moving small objects in 3D space, (2) an innovative physics-based tracking algorithm that integrates kinematics motion equations to handle outliers and missed detections, and (3) an outlier detection and correction module that significantly improves tracking performance in challenging scenarios such as occlusions and rapid direction changes. We evaluated our proposed system on a custom racquetball dataset. Our evaluation shows our system surpassing kalman filter based trackers with up to 70\% less Average Displacement Error. Our system has significant applications for improving robot perception on autonomous platforms and demonstrates the effectiveness of combining physics-based models with deep learning approaches for real-time 3D detection and tracking of challenging small objects.

cs.CV↗

arXiv2025

A multimodal stress detection dataset with facial expressions and physiological signals

Affective computing has garnered the attention and interest of researchers in recent years, as there is a need for AI systems to better understand and react to human emotions. However, analyzing human emotions, such as mood or stress, is quite complex. While various stress studies use facial expressions and wearables, most existing datasets rely on processing data from a single modality. This paper presents EmpathicSchool, a novel dataset that captures facial expressions and the associated physiological signals, such as heart rate, electrodermal activity, and skin temperature, under different stress levels. The data was collected from 30 participants during different sessions for about ninety minutes each (for a total of 40 hours). The data includes seven different signal types, including both computer vision and physiological features that can be used to detect stress. In addition, various experiments were conducted to validate the signal quality.

cs.MM↗

arXiv2025

An Analysis of Kalman Filter based Object Tracking Methods for Fast-Moving Tiny Objects

Unpredictable movement patterns and small visual mark make precise tracking of fast-moving tiny objects like a racquetball one of the challenging problems in computer vision. This challenge is particularly relevant for sport robotics applications, where lightweight and accurate tracking systems can improve robot perception and planning capabilities. While Kalman filter-based tracking methods have shown success in general object tracking scenarios, their performance degrades substantially when dealing with rapidly moving objects that exhibit irregular bouncing behavior. In this study, we evaluate the performance of five state-of-the-art Kalman filter-based tracking methods-OCSORT, DeepOCSORT, ByteTrack, BoTSORT, and StrongSORT-using a custom dataset containing 10,000 annotated racquetball frames captured at 720p-1280p resolution. We focus our analysis on two critical performance factors: inference speed and update frequency per image, examining how these parameters affect tracking accuracy and reliability for fast-moving tiny objects. Our experimental evaluation across four distinct scenarios reveals that DeepOCSORT achieves the lowest tracking error with an average ADE of 31.15 pixels compared to ByteTrack's 114.3 pixels, while ByteTrack demonstrates the fastest processing at 26.6ms average inference time versus DeepOCSORT's 26.8ms. However, our results show that all Kalman filter-based trackers exhibit significant tracking drift with spatial errors ranging from 3-11cm (ADE values: 31-114 pixels), indicating fundamental limitations in handling the unpredictable motion patterns of fast-moving tiny objects like racquetballs. Our analysis demonstrates that current tracking approaches require substantial improvements, with error rates 3-4x higher than standard object tracking benchmarks, highlighting the need for specialized methodologies for fast-moving tiny object tracking applications.

cs.CV↗

arXiv2025

UL-DD: A Multimodal Drowsiness Dataset Using Video, Biometric Signals, and Behavioral Data

In this study, we present a comprehensive public dataset for driver drowsiness detection, integrating multimodal signals of facial, behavioral, and biometric indicators. Our dataset includes 3D facial video using a depth camera, IR camera footage, posterior videos, and biometric signals such as heart rate, electrodermal activity, blood oxygen saturation, skin temperature, and accelerometer data. This data set provides grip sensor data from the steering wheel and telemetry data from the American truck simulator game to provide more information about drivers' behavior while they are alert and drowsy. Drowsiness levels were self-reported every four minutes using the Karolinska Sleepiness Scale (KSS). The simulation environment consists of three monitor setups, and the driving condition is completely like a car. Data were collected from 19 subjects (15 M, 4 F) in two conditions: when they were fully alert and when they exhibited signs of sleepiness. Unlike other datasets, our multimodal dataset has a continuous duration of 40 minutes for each data collection session per subject, contributing to a total length of 1,400 minutes, and we recorded gradual changes in the driver state rather than discrete alert/drowsy labels. This study aims to create a comprehensive multimodal dataset of driver drowsiness that captures a wider range of physiological, behavioral, and driving-related signals. The dataset will be available upon request to the corresponding author.

cs.CV↗

arXiv2025

From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems

LLMs when used with Retrieval Augmented Generation (RAG), are greatly improving the SOTA of translating natural language queries to structured and correct SQL. Unlike previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches that use (RAG) systems. We discuss benchmarks, evaluation methods, and evaluation metrics. Also, we uniquely study the use of Graph RAGs for better contextual accuracy and schema linking in these systems. Finally, we highlight key challenges such as computational efficiency, model robustness, and data privacy toward improvements of LLM-based text-to-SQL systems.

cs.CL↗

arXiv2024

TransFair: Transferring Fairness from Ocular Disease Classification to Progression Prediction

The use of artificial intelligence (AI) in automated disease classification significantly reduces healthcare costs and improves the accessibility of services. However, this transformation has given rise to concerns about the fairness of AI, which disproportionately affects certain groups, particularly patients from underprivileged populations. Recently, a number of methods and large-scale datasets have been proposed to address group performance disparities. Although these methods have shown effectiveness in disease classification tasks, they may fall short in ensuring fair prediction of disease progression, mainly because of limited longitudinal data with diverse demographics available for training a robust and equitable prediction model. In this paper, we introduce TransFair to enhance demographic fairness in progression prediction for ocular diseases. TransFair aims to transfer a fairness-enhanced disease classification model to the task of progression prediction with fairness preserved. Specifically, we train a fair EfficientNet, termed FairEN, equipped with a fairness-aware attention mechanism using extensive data for ocular disease classification. Subsequently, this fair classification model is adapted to a fair progression prediction model through knowledge distillation, which aims to minimize the latent feature distances between the classification and progression prediction models. We evaluate FairEN and TransFair for fairness-enhanced ocular disease classification and progression prediction using both two-dimensional (2D) and 3D retinal images. Extensive experiments and comparisons with models with and without considering fairness learning show that TransFair effectively enhances demographic equity in predicting ocular disease progression.

cs.LG↗

arXiv2024

A Multimodal Intermediate Fusion Network with Manifold Learning for Stress Detection

Multimodal deep learning methods capture synergistic features from multiple modalities and have the potential to improve accuracy for stress detection compared to unimodal methods. However, this accuracy gain typically comes from high computational cost due to the high-dimensional feature spaces, especially for intermediate fusion. Dimensionality reduction is one way to optimize multimodal learning by simplifying data and making the features more amenable to processing and analysis, thereby reducing computational complexity. This paper introduces an intermediate multimodal fusion network with manifold learning-based dimensionality reduction. The multimodal network generates independent representations from biometric signals and facial landmarks through 1D-CNN and 2D-CNN. Finally, these features are fused and fed to another 1D-CNN layer, followed by a fully connected dense layer. We compared various dimensionality reduction techniques for different variations of unimodal and multimodal networks. We observe that the intermediate-level fusion with the Multi-Dimensional Scaling (MDS) manifold method showed promising results with an accuracy of 96.00\% in a Leave-One-Subject-Out Cross-Validation (LOSO-CV) paradigm over other dimensional reduction methods. MDS had the highest computational cost among manifold learning methods. However, while outperforming other networks, it managed to reduce the computational cost of the proposed networks by 25\% when compared to six well-known conventional feature selection methods used in the preprocessing step.

cs.CV↗

arXiv2023

Multimodal Stress Detection Using Facial Landmarks and Biometric Signals

The development of various sensing technologies is improving measurements of stress and the well-being of individuals. Although progress has been made with single signal modalities like wearables and facial emotion recognition, integrating multiple modalities provides a more comprehensive understanding of stress, given that stress manifests differently across different people. Multi-modal learning aims to capitalize on the strength of each modality rather than relying on a single signal. Given the complexity of processing and integrating high-dimensional data from limited subjects, more research is needed. Numerous research efforts have been focused on fusing stress and emotion signals at an early stage, e.g., feature-level fusion using basic machine learning methods and 1D-CNN Methods. This paper proposes a multi-modal learning approach for stress detection that integrates facial landmarks and biometric signals. We test this multi-modal integration with various early-fusion and late-fusion techniques to integrate the 1D-CNN model from biometric signals and 2-D CNN using facial landmarks. We evaluate these architectures using a rigorous test of models' generalizability using the leave-one-subject-out mechanism, i.e., all samples related to a single subject are left out to train the model. Our findings show that late-fusion achieved 94.39\% accuracy, and early-fusion surpassed it with a 98.38\% accuracy rate. This research contributes valuable insights into enhancing stress detection through a multi-modal approach. The proposed research offers important knowledge in improving stress detection using a multi-modal approach.

cs.CV↗

arXiv2023

One-Class Classification for Intrusion Detection on Vehicular Networks

Controller Area Network bus systems within vehicular networks are not equipped with the tools necessary to ward off and protect themselves from modern cyber-security threats. Work has been done on using machine learning methods to detect and report these attacks, but common methods are not robust towards unknown attacks. These methods usually rely on there being a sufficient representation of attack data, which may not be available due to there either not being enough data present to adequately represent its distribution or the distribution itself is too diverse in nature for there to be a sufficient representation of it. With the use of one-class classification methods, this issue can be mitigated as only normal data is required to train a model for the detection of anomalous instances. Research has been done on the efficacy of these methods, most notably One-Class Support Vector Machine and Support Vector Data Description, but many new extensions of these works have been proposed and have yet to be tested for injection attacks in vehicular networks. In this paper, we investigate the performance of various state-of-the-art one-class classification methods for detecting injection attacks on Controller Area Network bus traffic. We investigate the effectiveness of these techniques on attacks launched on Controller Area Network buses from two different vehicles during normal operation and while being attacked. We observe that the Subspace Support Vector Data Description method outperformed all other tested methods with a Gmean of about 85%.

cs.LG↗

arXiv2022

A multimodal sensor dataset for continuous stress detection of nurses in a hospital

Advances in wearable technologies provide the opportunity to monitor many physiological variables continuously. Stress detection has gained increased attention in recent years, mainly because early stress detection can help individuals better manage health to minimize the negative impacts of long-term stress exposure. This paper provides a unique stress detection dataset created in a natural working environment in a hospital. This dataset is a collection of biometric data of nurses during the COVID-19 outbreak. Studying stress in a work environment is complex due to many social, cultural, and psychological factors in dealing with stressful conditions. Therefore, we captured both the physiological data and associated context pertaining to the stress events. We monitored specifc physiological variables such as electrodermal activity, Heart Rate, and skin temperature of the nurse subjects. A periodic smartphone-administered survey also captured the contributing factors for the detected stress events. A database containing the signals, stress events, and survey responses is publicly available on Dryad.

cs.CY↗

arXiv2019

Deep Multi-view Learning to Rank

We study the problem of learning to rank from multiple information sources. Though multi-view learning and learning to rank have been studied extensively leading to a wide range of applications, multi-view learning to rank as a synergy of both topics has received little attention. The aim of the paper is to propose a composite ranking method while keeping a close correlation with the individual rankings simultaneously. We present a generic framework for multi-view subspace learning to rank (MvSL2R), and two novel solutions are introduced under the framework. The first solution captures information of feature mappings from within each view as well as across views using autoencoder-like networks. Novel feature embedding methods are formulated in the optimization of multi-view unsupervised and discriminant autoencoders. Moreover, we introduce an end-to-end solution to learning towards both the joint ranking objective and the individual rankings. The proposed solution enhances the joint ranking with minimum view-specific ranking loss, so that it can achieve the maximum global view agreements in a single optimization process. The proposed method is evaluated on three different ranking problems, i.e. university ranking, multi-view lingual text ranking and image data ranking, providing superior results compared to related methods.

cs.LG↗

arXiv2019

ClustCrypt: Privacy-Preserving Clustering of Unstructured Big Data in the Cloud

Security and confidentiality of big data stored in the cloud are important concerns for many organizations to adopt cloud services. One common approach to address the concerns is client-side encryption where data is encrypted on the client machine before being stored in the cloud. Having encrypted data in the cloud, however, limits the ability of data clustering, which is a crucial part of many data analytics applications, such as search systems. To overcome the limitation, in this paper, we present an approach named ClustCrypt for efficient topic-based clustering of encrypted unstructured big data in the cloud. ClustCrypt dynamically estimates the optimal number of clusters based on the statistical characteristics of encrypted data. It also provides clustering approach for encrypted data. We deploy ClustCrypt within the context of a secure cloud-based semantic search system (S3BD). Experimental results obtained from evaluating ClustCrypt on three datasets demonstrate on average 60% improvement on clusters' coherency. ClustCrypt also decreases the search-time overhead by up to 78% and increases the accuracy of search results by up to 35%

cs.CR↗

arXiv2019

Edge Computing for User-Centric Secure Search on Cloud-Based Encrypted Big Data

Cloud service providers offer a low-cost and convenient solution to host unstructured data. However, cloud services act as third-party solutions and do not provide control of the data to users. This has raised security and privacy concerns for many organizations (users) with sensitive data to utilize cloud-based solutions. User-side encryption can potentially address these concerns by establishing user-centric cloud services and granting data control to the user. Nonetheless, user-side encryption limits the ability to process (e.g., search) encrypted data on the cloud. Accordingly, in this research, we provide a framework that enables processing (in particular, searching) of encrypted multi-organizational (i.e., multi-source) big data without revealing the data to cloud provider. Our framework leverages locality feature of edge computing to offer a user-centric search ability in a real-time manner. In particular, the edge system intelligently predicts the user's search pattern and prunes the multi-source big data search space to reduce the search time. The pruning system is based on efficient sampling from the clustered big dataset on the cloud. For each cluster, the pruning system dynamically samples appropriate number of terms based on the user's search tendency, so that the cluster is optimally represented. We developed a prototype of a user-centric search system and evaluated it against multiple datasets. Experimental results demonstrate 27% improvement in the pruning quality and search accuracy.

cs.CR↗